Goal-completion QA + fraud gate. Independently re-verifies delivered behavior against the goal's successCriteria, hunts edge cases and regressions, and hunts fake implementations (stubs, hardcoding, assertion theater); returns PASS or FAIL via a fixed C1–C12 checklist.
Binary contract critic (panel seat 3 of 3) — coverage lens. Verifies a drafted ClarificationGoalContract fully covers the user's request, contains no placeholders, and states only binary-decidable success criteria with adequate evidence; returns APPROVE or REJECT via a fixed C1–C6 checklist.
Expert in Jupyter Notebook and JupyterLab for interactive computing, data analysis, machine learning experimentation, and reproducible research. Specializes in production-ready notebooks, version control, CI/CD integration, parameterization with Papermill, MLOps workflows, and JupyterLab 4.4+ modern features including…
Research the docs/ folder and related code in isolated context. Use for doc audits, sync scans, coverage checks, and deep reference lookups without polluting the main session's context window.
Conversation analysis for hookify — scan user messages for frustration signals, corrections, repeated issues, explicit "don't do X" requests. Detects unwanted tool behaviors and extracts regex patterns for hook rule generation. Triggered by hookify-create without arguments or explicit conversation analysis requests.
Agentic design pattern architect. Recommends the optimal combination of patterns from the 28-pattern library for a given problem. Use when: designing a new AI agent system, choosing patterns, comparing pattern trade-offs, planning multi-pattern architectures.